Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
SWE-Bench Verified
42%38%
GPQA Diamond
59.1%69.5%
MMLU
88.5%90.8%
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Feb 27 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4.5 leads DeepSeek V3 on 2 of the 3 benchmarks they both report (SWE-Bench Verified, GPQA Diamond, MMLU). DeepSeek V3 shipped 63 days before GPT-4.5, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 128k (GPT-4.5). DeepSeek V3 is open weight, while GPT-4.5 is closed.

On SWE-Bench Verified, DeepSeek V3 leads at 42% vs GPT-4.5 at 38%. On GPQA Diamond, GPT-4.5 leads at 69.5% vs DeepSeek V3 at 59.1%. On MMLU, GPT-4.5 leads at 90.8% vs DeepSeek V3 at 88.5%.